Data-Free Metrics Don't Work: The Missing Invariance Under Functionally Preserving Reparameterisations
cs.LG, cs.AI
Submitted: 2026-11-11
Updated: 2026-11-11
Project page: https://gmw99.github.io/data-free-metrics-dont-work
Terminology
Sources
- One Billion Word Benchmark for Measuring Progress in Statistical Language Modeling
- Early-stopping for Transformer model training
- HTMuon: Improving Muon via Heavy-Tailed Spectral Correction
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Approaching Deep Learning through the Spectral Dynamics of Weights
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis